{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:28:40Z","timestamp":1783787320228,"version":"3.55.0"},"publisher-location":"Cham","reference-count":106,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729911","type":"print"},{"value":"9783031729928","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72992-8_24","type":"book-chapter","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T08:29:02Z","timestamp":1730190542000},"page":"421-440","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":47,"title":["Scene Coordinate Reconstruction: Posing of\u00a0Image Collections via\u00a0Incremental Learning of\u00a0a\u00a0Relocalizer"],"prefix":"10.1007","author":[{"given":"Eric","family":"Brachmann","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jamie","family":"Wynn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tommaso","family":"Cavallari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"\u00c1ron","family":"Monszpart","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniyar","family":"Turmukhambetov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Victor Adrian","family":"Prisacariu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,30]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Agarwal, S., et al.: Building Rome in a day. ACM TOG (2011)","DOI":"10.1145\/2001269.2001293"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Agarwal, S., Snavely, N., Seitz, S.M., Szeliski, R.: Bundle adjustment in the large. In: ECCV (2010)","DOI":"10.1007\/978-3-642-15552-9_3"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Arnold, E., et al.: Map-free visual relocalization: metric pose relative to a single image. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19769-7_40"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Balntas, V., Li, S., Prisacariu, V.A.: RelocNet: continuous metric learning relocalisation using neural nets. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01264-9_46"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Verbin, D., Srinivasan, P.P., Hedman, P.: Mip-NeRF 360: unbounded anti-aliased neural radiance fields. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"24_CR6","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1023\/A:1007923216416","volume":"23","author":"PA Beardsley","year":"1997","unstructured":"Beardsley, P.A., Zisserman, A., Murray, D.W.: Sequential updating of projective and affine structure from motion. IJCV 23, 235\u2013259 (1997)","journal-title":"IJCV"},{"key":"24_CR7","unstructured":"Bhat, S.F., Birkl, R., Wofk, D., Wonka, P., M\u00fcller, M.: ZoeDepth: zero-shot transfer by combining relative and metric depth. arXiv (2023)"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Bhowmick, B., Patra, S., Chatterjee, A., Govindu, V.M., Banerjee, S.: Divide and conquer: efficient large-scale structure from motion using graph partitioning. In: ACCV (2015)","DOI":"10.1007\/978-3-319-16808-1_19"},{"key":"24_CR9","first-page":"190","volume":"157","author":"B Bhowmick","year":"2017","unstructured":"Bhowmick, B., Patra, S., Chatterjee, A., Govindu, V.M., Banerjee, S.: Divide and conquer: a hierarchical approach to large-scale structure-from-motion. CVIU 157, 190\u2013205 (2017)","journal-title":"CVIU"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Bian, W., Wang, Z., Li, K., Bian, J.W., Prisacariu, V.A.: NoPe-NeRF: optimising neural radiance field with no pose prior. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00405"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Bloesch, M., Czarnowski, J., Clark, R., Leutenegger, S., Davison, A.J.: CodeSLAM \u2014 learning a compact, optimisable representation for dense visual SLAM. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00271"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Cavallari, T., Prisacariu, V.A.: Accelerated coordinate encoding: learning to relocalize in minutes using RGB and poses. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00488"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Humenberger, M., Rother, C., Sattler, T.: On the limits of pseudo ground truth in visual camera re-localisation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00616"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Brachmann, E., et al.: DSAC-differentiable RANSAC for camera localization. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.267"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Rother, C.: Learning less is more-6D camera localization via 3D surface regression. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00489"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Rother, C.: Expert sample consensus applied to camera re-localization. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00762"},{"issue":"9","key":"24_CR17","first-page":"5847","volume":"44","author":"E Brachmann","year":"2021","unstructured":"Brachmann, E., Rother, C.: Visual camera re-localization from RGB and RGB-D images using DSAC. IEEE TPAMI 44(9), 5847\u20135865 (2021)","journal-title":"IEEE TPAMI"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Br\u00e9gier, R.: Deep regression on manifolds: a 3D rotation case study. In: 3DV (2021)","DOI":"10.1109\/3DV53792.2021.00027"},{"key":"24_CR19","unstructured":"Brown, D.: The bundle adjustment-progress and prospect. In: Congress of the International Society for Photogrammetry (1976)"},{"key":"24_CR20","unstructured":"Brown, M., Lowe, D.G.: Unsupervised 3D object recognition and reconstruction in unordered datasets. In: 3DIM (2005)"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Carlone, L., Tron, R., Daniilidis, K., Dellaert, F.: Initialization techniques for 3D SLAM: a survey on rotation estimation and its use in pose graph optimization. In: ICRA (2015)","DOI":"10.1109\/ICRA.2015.7139836"},{"key":"24_CR22","doi-asserted-by":"crossref","unstructured":"Cavallari, T., Bertinetto, L., Mukhoti, J., Torr, P.H., Golodetz, S.: Let\u2019s take this online: adapting scene coordinate regression network predictions for online RGB-D camera relocalisation. In: 3DV (2019)","DOI":"10.1109\/3DV.2019.00068"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Cavallari, T., Golodetz, S., Lord, N.A., Valentin, J., Di\u00a0Stefano, L., Torr, P.H.: On-the-fly adaptation of regression forests for online camera relocalisation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.31"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Chen, S., Bhalgat, Y., Li, X., Bian, J., Li, K., Wang, Z., Prisacariu, V.A.: Neural refinement for absolute pose regression with feature synthesis. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01983"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Chen, S., Li, X., Wang, Z., Prisacariu, V.: DFNet: enhance absolute pose regression with direct feature matching. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20080-9_1"},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Chen, S., Wang, Z., Prisacariu, V.: Direct-PoseNet: absolute pose regression with photometric consistency. In: 3DV (2021)","DOI":"10.1109\/3DV53792.2021.00125"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Esteves, C., Jampani, V., Kar, A., Maji, S., Makadia, A.: LU-NeRF: scene and pose estimation by synchronizing local unposed NeRFs. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01679"},{"key":"24_CR28","doi-asserted-by":"crossref","unstructured":"Crandall, D., Owens, A., Snavely, N., Huttenlocher, D.: Discrete-continuous optimization for large-scale structure from motion. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995626"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Davison, A.J.: Real-time simultaneous localisation and mapping with a single camera. In: ICCV (2003)","DOI":"10.1109\/ICCV.2003.1238654"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperPoint: self-supervised interest point detection and description. In: CVPRW (2018)","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"24_CR32","doi-asserted-by":"crossref","unstructured":"Ding, M., Wang, Z., Sun, J., Shi, J., Luo, P.: CamNet: coarse-to-fine retrieval for camera re-localization. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00296"},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Dusmanu, M., et al.: D2-net: a trainable CNN for joint description and detection of local features. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00828"},{"issue":"6","key":"24_CR34","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/358669.358692","volume":"24","author":"MA Fischler","year":"1981","unstructured":"Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381\u2013395 (1981)","journal-title":"Commun. ACM"},{"issue":"8","key":"24_CR35","doi-asserted-by":"publisher","first-page":"930","DOI":"10.1109\/TPAMI.2003.1217599","volume":"25","author":"XS Gao","year":"2003","unstructured":"Gao, X.S., Hou, X.R., Tang, J., Cheng, H.F.: Complete solution classification for the perspective-three-point problem. IEEE TPAMI 25(8), 930\u2013943 (2003)","journal-title":"IEEE TPAMI"},{"key":"24_CR36","doi-asserted-by":"crossref","unstructured":"Gherardi, R., Farenzena, M., Fusiello, A.: Improving the efficiency of hierarchical structure-and-motion. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539782"},{"key":"24_CR37","unstructured":"Govindu, V.M.: Combining two-view constraints for motion estimation. In: CVPR (2001)"},{"key":"24_CR38","unstructured":"Govindu, V.M.: Lie-algebraic averaging for globally consistent motion estimation. In: CVPR (2004)"},{"key":"24_CR39","doi-asserted-by":"crossref","unstructured":"Hartley, R., Trumpf, J., Dai, Y., Li, H.: Rotation averaging. IJCV (2013)","DOI":"10.1007\/s11263-012-0601-0"},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2003)","DOI":"10.1017\/CBO9780511811685"},{"key":"24_CR41","doi-asserted-by":"crossref","unstructured":"He, X., et al.: Detector-free structure from motion. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02040"},{"key":"24_CR42","doi-asserted-by":"crossref","unstructured":"Heinly, J., Sch\u00f6nberger, J.L., Dunn, E., Frahm, J.M.: Reconstructing the World in six days. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298949"},{"issue":"7","key":"24_CR43","doi-asserted-by":"publisher","first-page":"1811","DOI":"10.1007\/s11263-022-01615-7","volume":"130","author":"M Humenberger","year":"2022","unstructured":"Humenberger, M., et al.: Investigating the role of image retrieval for visual localization: an exhaustive benchmark. IJCV 130(7), 1811\u20131836 (2022)","journal-title":"IJCV"},{"key":"24_CR44","doi-asserted-by":"crossref","unstructured":"Izadi, S., et al.: KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera. In: UIST (2011)","DOI":"10.1145\/2047196.2047270"},{"key":"24_CR45","doi-asserted-by":"crossref","unstructured":"Jeong, Y., Ahn, S., Choy, C., Anandkumar, A., Cho, M., Park, J.: Self-calibrating neural radiance fields. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00579"},{"issue":"2","key":"24_CR46","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1007\/s11263-020-01385-0","volume":"129","author":"Y Jin","year":"2021","unstructured":"Jin, Y., et al.: Image matching across wide baselines: from paper to practice. IJCV 129(2), 517\u2013547 (2021)","journal-title":"IJCV"},{"key":"24_CR47","doi-asserted-by":"crossref","unstructured":"Kendall, A., Grimes, M., Cipolla, R.: PoseNet: a convolutional network for real-time 6-DoF camera relocalization. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.336"},{"key":"24_CR48","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D gaussian splatting for real-time radiance field rendering. ACM TOG (2023)","DOI":"10.1145\/3592433"},{"issue":"4","key":"24_CR49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073599","volume":"36","author":"A Knapitsch","year":"2017","unstructured":"Knapitsch, A., Park, J., Zhou, Q.Y., Koltun, V.: Tanks and temples: benchmarking large-scale scene reconstruction. ACM TOG 36(4), 1\u201313 (2017)","journal-title":"ACM TOG"},{"key":"24_CR50","unstructured":"Kraus, K.: Photogrammetry. No.\u00a0v. 1 in Photogrammetry, Ferdinand Dummlers Verlag (1993)"},{"key":"24_CR51","doi-asserted-by":"crossref","unstructured":"Laskar, Z., Melekhov, I., Kalia, S., Kannala, J.: Camera relocalization by computing pairwise relative poses using convolutional neural network. In: ICCV Workshops (2017)","DOI":"10.1109\/ICCVW.2017.113"},{"key":"24_CR52","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, S., Zhao, Y., Verbeek, J., Kannala, J.: Hierarchical scene coordinate classification and regression for visual localization. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01200"},{"key":"24_CR53","doi-asserted-by":"crossref","unstructured":"Lin, A., Zhang, J.Y., Ramanan, D., Tulsiani, S.: Relpose++: recovering 6D poses from sparse-view observations. In: 3DV (2024)","DOI":"10.1109\/3DV62453.2024.00126"},{"key":"24_CR54","doi-asserted-by":"crossref","unstructured":"Lin, C.H., Ma, W.C., Torralba, A., Lucey, S.: BARF: bundle-adjusting neural radiance fields. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00569"},{"key":"24_CR55","doi-asserted-by":"crossref","unstructured":"Lin, Y., et al.: Parallel inversion of neural radiance fields for robust pose estimation. In: ICRA (2023)","DOI":"10.1109\/ICRA48891.2023.10161117"},{"key":"24_CR56","doi-asserted-by":"crossref","unstructured":"Lindenberger, P., Sarlin, P.E., Pollefeys, M.: LightGlue: local feature matching at light speed. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01616"},{"key":"24_CR57","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"24_CR58","doi-asserted-by":"crossref","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV (2004)","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"24_CR59","doi-asserted-by":"crossref","unstructured":"Martinec, D., Pajdla, T.: Robust rotation and translation estimation in multiview reconstruction. In: CVPR (2007)","DOI":"10.1109\/CVPR.2007.383115"},{"key":"24_CR60","doi-asserted-by":"crossref","unstructured":"Meng, Q., et al.: GNeRF: GAN-based neural radiance field without posed camera. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00629"},{"key":"24_CR61","doi-asserted-by":"crossref","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"24_CR62","doi-asserted-by":"crossref","unstructured":"Moreau, A., Piasco, N., Bennehar, M., Tsishkou, D., Stanciulescu, B., de\u00a0La\u00a0Fortelle, A.: CROSSFIRE: camera relocalization on self-supervised features from an implicit representation. ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00030"},{"key":"24_CR63","doi-asserted-by":"crossref","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. ACM TOG (2022)","DOI":"10.1145\/3528223.3530127"},{"key":"24_CR64","doi-asserted-by":"crossref","unstructured":"Newcombe, R., et al.: KinectFusion: real-time dense surface mapping and tracking. In: ISMAR (2011)","DOI":"10.1109\/ISMAR.2011.6092378"},{"key":"24_CR65","unstructured":"Nist\u00e9r, D., Naroditsky, O., Bergen, J.: Visual odometry. In: CVPR (2004)"},{"key":"24_CR66","doi-asserted-by":"crossref","unstructured":"Pollefeys, M., Koch, R., Vergauwen, M., Van Gool, L.: Automated reconstruction of 3D scenes from sequences of images. J. Photogr. Rem. Sens. (2000)","DOI":"10.1016\/S0924-2716(00)00023-X"},{"key":"24_CR67","doi-asserted-by":"crossref","unstructured":"Rau, A., Garcia-Hernando, G., Stoyanov, D., Brostow, G.J., Turmukhambetov, D.: Predicting visual overlap of images through interpretable non-metric box embeddings. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58558-7_37"},{"key":"24_CR68","unstructured":"Reality, C.: Reality Capture (2016). https:\/\/www.capturingreality.com\/realitycapture. Accessed 15 Nov 2023"},{"key":"24_CR69","doi-asserted-by":"crossref","unstructured":"Reizenstein, J., Shapovalov, R., Henzler, P., Sbordone, L., Labatut, P., Novotny, D.: Common objects in 3D: large-scale learning and evaluation of real-life 3D category reconstruction. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"24_CR70","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., Cadena, C., Siegwart, R., Dymczyk, M.: From coarse to fine: robust hierarchical localization at large scale. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01300"},{"key":"24_CR71","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperGlue: learning feature matching with graph neural networks. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"24_CR72","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., et al.: Back to the feature: learning robust camera localization from pixels to pose. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00326"},{"key":"24_CR73","doi-asserted-by":"crossref","unstructured":"Sattler, T., Leibe, B., Kobbelt, L.: Fast image-based localization using direct 2D-to-3D matching. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126302"},{"key":"24_CR74","doi-asserted-by":"crossref","unstructured":"Sattler, T., Leibe, B., Kobbelt, L.: Improving image-based localization by active correspondence search. In: ECCV (2012)","DOI":"10.1007\/978-3-642-33718-5_54"},{"issue":"9","key":"24_CR75","doi-asserted-by":"publisher","first-page":"1744","DOI":"10.1109\/TPAMI.2016.2611662","volume":"39","author":"T Sattler","year":"2016","unstructured":"Sattler, T., Leibe, B., Kobbelt, L.: Efficient & effective prioritized matching for large-scale image-based localization. IEEE TPAMI 39(9), 1744\u20131756 (2016)","journal-title":"IEEE TPAMI"},{"key":"24_CR76","doi-asserted-by":"crossref","unstructured":"Sattler, T., et al.: Are large-scale 3D models really necessary for accurate visual localization? In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.654"},{"key":"24_CR77","doi-asserted-by":"crossref","unstructured":"Sattler, T., Zhou, Q., Pollefeys, M., Leal-Taixe, L.: Understanding the limitations of CNN-based absolute camera pose regression. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00342"},{"key":"24_CR78","doi-asserted-by":"crossref","unstructured":"Schaffalitzky, F., Zisserman, A.: Multi-view matching for unordered image sets, or \u201chow do i organize my holiday snaps?\u201d. In: ECCV (2002)","DOI":"10.1007\/3-540-47969-4_28"},{"key":"24_CR79","unstructured":"Sch\u00f6nberger, J.L.: Colmap Github Issues (2017). https:\/\/github.com\/colmap\/colmap\/issues\/116#issuecomment-298926277. Accessed 15 Nov 2023"},{"key":"24_CR80","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"24_CR81","doi-asserted-by":"crossref","unstructured":"Shotton, J., Glocker, B., Zach, C., Izadi, S., Criminisi, A., Fitzgibbon, A.: Scene coordinate regression forests for camera relocalization in RGB-D images. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.377"},{"key":"24_CR82","doi-asserted-by":"crossref","unstructured":"Sinha, S., Zhang, J.Y., Tagliasacchi, A., Gilitschenski, I., Lindell, D.B.: SparsePose: sparse-view camera pose regression and refinement. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02045"},{"key":"24_CR83","doi-asserted-by":"crossref","unstructured":"Smith, L.N., Topin, N.: Super-convergence: very fast training of neural networks using large learning rates. In: Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications (2019)","DOI":"10.1117\/12.2520589"},{"key":"24_CR84","doi-asserted-by":"crossref","unstructured":"Snavely, N., Seitz, S.M., Szeliski, R.: Photo tourism: exploring photo collections in 3D. ACM TOG (2006)","DOI":"10.1145\/1141911.1141964"},{"key":"24_CR85","doi-asserted-by":"crossref","unstructured":"Snavely, N., Seitz, S.M., Szeliski, R.: Modeling the world from internet photo collections. IJCV (2008)","DOI":"10.1007\/s11263-007-0107-3"},{"key":"24_CR86","doi-asserted-by":"crossref","unstructured":"Snavely, N., Seitz, S.M., Szeliski, R.: Skeletal graphs for efficient structure from motion. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587678"},{"key":"24_CR87","doi-asserted-by":"crossref","unstructured":"Sun, J., Shen, Z., Wang, Y., Bao, H., Zhou, X.: LoFTR: detector-free local feature matching with transformers. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00881"},{"issue":"1","key":"24_CR88","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1006\/jvci.1994.1002","volume":"5","author":"R Szeliski","year":"1994","unstructured":"Szeliski, R., Kang, S.B.: Recovering 3D shape and motion from image streams using nonlinear least squares. J. Vis. Comut. Image Repr. 5(1), 10\u201328 (1994)","journal-title":"J. Vis. Comut. Image Repr."},{"key":"24_CR89","doi-asserted-by":"crossref","unstructured":"Tancik, M., et al.: Nerfstudio: a modular framework for neural radiance field development. In: ACM TOG (2023)","DOI":"10.1145\/3588432.3591516"},{"key":"24_CR90","unstructured":"Teed, Z., Deng, J.: DROID-SLAM: deep visual SLAM for monocular, stereo, and RGB-D cameras. In: NeurIPS (2021)"},{"key":"24_CR91","doi-asserted-by":"crossref","unstructured":"Toldo, R., Gherardi, R., Farenzena, M., Fusiello, A.: Hierarchical structure-and-motion recovery from uncalibrated images. CVIU (2015)","DOI":"10.1016\/j.cviu.2015.05.011"},{"key":"24_CR92","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1007\/3-540-44480-7_21","volume-title":"Vision Algorithms: Theory and Practice","author":"B Triggs","year":"2000","unstructured":"Triggs, B., McLauchlan, P.F., Hartley, R.I., Fitzgibbon, A.W.: Bundle adjustment \u2014 a modern synthesis. In: Triggs, B., Zisserman, A., Szeliski, R. (eds.) IWVA 1999. LNCS, vol. 1883, pp. 298\u2013372. Springer, Heidelberg (2000). https:\/\/doi.org\/10.1007\/3-540-44480-7_21"},{"key":"24_CR93","doi-asserted-by":"crossref","unstructured":"T\u00fcrko\u011flu, M.\u00d6., Brachmann, E., Schindler, K., Brostow, G., Monszpart, A.: Visual camera re-localization using graph neural networks and relative pose supervision. In: 3DV (2021)","DOI":"10.1109\/3DV53792.2021.00025"},{"key":"24_CR94","unstructured":"Ulyanov, D., Vedaldi, A., Lempitsky, V.: Deep image prior. In: CVPR (2018)"},{"key":"24_CR95","doi-asserted-by":"crossref","unstructured":"Ummenhofer, B., et al.: DeMoN: depth and motion network for learning monocular stereo. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.596"},{"issue":"1","key":"24_CR96","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2999533","volume":"36","author":"M Waechter","year":"2017","unstructured":"Waechter, M., Beljan, M., Fuhrmann, S., Moehrle, N., Kopf, J., Goesele, M.: Virtual rephotography: novel view prediction error for 3D reconstruction. ACM TOG 36(1), 1\u201311 (2017)","journal-title":"ACM TOG"},{"key":"24_CR97","doi-asserted-by":"crossref","unstructured":"Wang, S., Leroy, V., Cabon, Y., Chidlovskii, B., Revaud, J.: DUSt3R: geometric 3D vision made easy. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"24_CR98","unstructured":"Wang, Z., Wu, S., Xie, W., Chen, M., Prisacariu, V.A.: NeRF\u2013: neural radiance fields without known camera parameters. arXiv (2021)"},{"key":"24_CR99","doi-asserted-by":"crossref","unstructured":"Wei, X., Zhang, Y., Li, Z., Fu, Y., Xue, X.: DeepSFM: structure from motion via deep bundle adjustment. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58452-8_14"},{"key":"24_CR100","doi-asserted-by":"crossref","unstructured":"Wu, C.: Towards linear-time incremental structure from motion. In: 3DV (2013)","DOI":"10.1109\/3DV.2013.25"},{"key":"24_CR101","unstructured":"Xia, Y., Tang, H., Timofte, R., Van\u00a0Gool, L.: SiNeRF: sinusoidal neural radiance fields for joint pose estimation and scene reconstruction. In: BMVC (2022)"},{"key":"24_CR102","doi-asserted-by":"crossref","unstructured":"Yen-Chen, L., Florence, P., Barron, J.T., Rodriguez, A., Isola, P., Lin, T.Y.: iNeRF: inverting neural radiance fields for pose estimation. In: IROS (2021)","DOI":"10.1109\/IROS51168.2021.9636708"},{"key":"24_CR103","unstructured":"Zhang, J.Y., Lin, A., Kumar, M., Yang, T.H., Ramanan, D., Tulsiani, S.: Cameras as rays: pose estimation via ray diffusion. In: ICLR (2024)"},{"key":"24_CR104","doi-asserted-by":"crossref","unstructured":"Zhang, W., Kosecka, J.: Image based localization in urban environments. In: 3DPVT (2006)","DOI":"10.1109\/3DPVT.2006.80"},{"key":"24_CR105","doi-asserted-by":"crossref","unstructured":"Zhou, Q., Sattler, T., Pollefeys, M., Leal-Taixe, L.: To learn or not to learn: visual localization from essential matrices. In: ICRA (2020)","DOI":"10.1109\/ICRA40945.2020.9196607"},{"key":"24_CR106","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Barnes, C., Jingwan, L., Jimei, Y., Hao, L.: On the continuity of rotation representations in neural networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00589"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72992-8_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T08:49:08Z","timestamp":1730191748000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72992-8_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,30]]},"ISBN":["9783031729911","9783031729928"],"references-count":106,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72992-8_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,30]]},"assertion":[{"value":"30 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}